From 7e89e4aaa9ae83107d059c186955484b3aa6eb23 Mon Sep 17 00:00:00 2001 From: Ivan Mironov Date: Thu, 25 Jun 2020 21:50:42 +0500 Subject: drm/amd/powerplay: Fix NULL dereference in lock_bus() on Vega20 w/o RAS I updated my system with Radeon VII from kernel 5.6 to kernel 5.7, and following started to happen on each boot: ... BUG: kernel NULL pointer dereference, address: 0000000000000128 ... CPU: 9 PID: 1940 Comm: modprobe Tainted: G E 5.7.2-200.im0.fc32.x86_64 #1 Hardware name: System manufacturer System Product Name/PRIME X570-P, BIOS 1407 04/02/2020 RIP: 0010:lock_bus+0x42/0x60 [amdgpu] ... Call Trace: i2c_smbus_xfer+0x3d/0xf0 i2c_default_probe+0xf3/0x130 i2c_detect.isra.0+0xfe/0x2b0 ? kfree+0xa3/0x200 ? kobject_uevent_env+0x11f/0x6a0 ? i2c_detect.isra.0+0x2b0/0x2b0 __process_new_driver+0x1b/0x20 bus_for_each_dev+0x64/0x90 ? 0xffffffffc0f34000 i2c_register_driver+0x73/0xc0 do_one_initcall+0x46/0x200 ? _cond_resched+0x16/0x40 ? kmem_cache_alloc_trace+0x167/0x220 ? do_init_module+0x23/0x260 do_init_module+0x5c/0x260 __do_sys_init_module+0x14f/0x170 do_syscall_64+0x5b/0xf0 entry_SYSCALL_64_after_hwframe+0x44/0xa9 ... Error appears when some i2c device driver tries to probe for devices using adapter registered by `smu_v11_0_i2c_eeprom_control_init()`. Code supporting this adapter requires `adev->psp.ras.ras` to be not NULL, which is true only when `amdgpu_ras_init()` detects HW support by calling `amdgpu_ras_check_supported()`. Before 9015d60c9ee1, adapter was registered by -> amdgpu_device_ip_init() -> amdgpu_ras_recovery_init() -> amdgpu_ras_eeprom_init() -> smu_v11_0_i2c_eeprom_control_init() after verifying that `adev->psp.ras.ras` is not NULL in `amdgpu_ras_recovery_init()`. Currently it is registered unconditionally by -> amdgpu_device_ip_init() -> pp_sw_init() -> hwmgr_sw_init() -> vega20_smu_init() -> smu_v11_0_i2c_eeprom_control_init() Fix simply adds HW support check (ras == NULL => no support) before calling `smu_v11_0_i2c_eeprom_control_{init,fini}()`. Please note that there is a chance that similar fix is also required for CHIP_ARCTURUS. I do not know whether any actual Arcturus hardware without RAS exist, and whether calling `smu_i2c_eeprom_init()` makes any sense when there is no HW support. Cc: stable@vger.kernel.org Fixes: 9015d60c9ee1 ("drm/amdgpu: Move EEPROM I2C adapter to amdgpu_device") Signed-off-by: Ivan Mironov Tested-by: Bjorn Nostvold Signed-off-by: Alex Deucher --- drivers/gpu/drm/amd/powerplay/smumgr/vega20_smumgr.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/vega20_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/vega20_smumgr.c index 2fb97554134f..c2e0fbbccf56 100644 --- a/drivers/gpu/drm/amd/powerplay/smumgr/vega20_smumgr.c +++ b/drivers/gpu/drm/amd/powerplay/smumgr/vega20_smumgr.c @@ -522,9 +522,11 @@ static int vega20_smu_init(struct pp_hwmgr *hwmgr) priv->smu_tables.entry[TABLE_ACTIVITY_MONITOR_COEFF].version = 0x01; priv->smu_tables.entry[TABLE_ACTIVITY_MONITOR_COEFF].size = sizeof(DpmActivityMonitorCoeffInt_t); - ret = smu_v11_0_i2c_eeprom_control_init(&adev->pm.smu_i2c); - if (ret) - goto err4; + if (adev->psp.ras.ras) { + ret = smu_v11_0_i2c_eeprom_control_init(&adev->pm.smu_i2c); + if (ret) + goto err4; + } return 0; @@ -560,7 +562,8 @@ static int vega20_smu_fini(struct pp_hwmgr *hwmgr) (struct vega20_smumgr *)(hwmgr->smu_backend); struct amdgpu_device *adev = hwmgr->adev; - smu_v11_0_i2c_eeprom_control_fini(&adev->pm.smu_i2c); + if (adev->psp.ras.ras) + smu_v11_0_i2c_eeprom_control_fini(&adev->pm.smu_i2c); if (priv) { amdgpu_bo_free_kernel(&priv->smu_tables.entry[TABLE_PPTABLE].handle, -- cgit v1.2.3 From 6eb3cf2e06d22b2b08e6b0ab48cb9c05a8e1a107 Mon Sep 17 00:00:00 2001 From: Nicholas Kazlauskas Date: Mon, 29 Jun 2020 13:03:52 -0400 Subject: drm/amd/display: Only revalidate bandwidth on medium and fast updates [Why] Changes that are fast don't require updating DLG parameters making this call unnecessary. Considering this is an expensive call it should not be done on every flip. DML touches clocks, p-state support, DLG params and a few other DC internal flags and these aren't expected during fast. A hang has been reported with this change when called on every flip which suggests that modifying these fields is not recommended behavior on fast updates. [How] Guard the validation to only happen if update type isn't FAST. Bug: https://gitlab.freedesktop.org/drm/amd/-/issues/1191 Fixes: a24eaa5c51255b ("drm/amd/display: Revalidate bandwidth before commiting DC updates") Signed-off-by: Nicholas Kazlauskas Acked-by: Alex Deucher Reviewed-by: Roman Li Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/display/dc/core/dc.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 6f93a6ca4cf0..d016f50e187c 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -2538,10 +2538,12 @@ void dc_commit_updates_for_stream(struct dc *dc, copy_stream_update_to_stream(dc, context, stream, stream_update); - if (!dc->res_pool->funcs->validate_bandwidth(dc, context, false)) { - DC_ERROR("Mode validation failed for stream update!\n"); - dc_release_state(context); - return; + if (update_type > UPDATE_TYPE_FAST) { + if (!dc->res_pool->funcs->validate_bandwidth(dc, context, false)) { + DC_ERROR("Mode validation failed for stream update!\n"); + dc_release_state(context); + return; + } } commit_planes_for_stream( -- cgit v1.2.3 From d7a6634a4cfba073ff6a526cb4265d6e58ece234 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Thu, 25 Jun 2020 17:55:57 -0400 Subject: drm/amdgpu/atomfirmware: fix vram_info fetching for renoir Renoir uses integrated_system_info table v12. The table has the same layout as v11 with respect to this data. Just reuse the existing code for v12 for stable. Fixes incorrectly reported vram info in the driver output. Acked-by: Evan Quan Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c index 58f9d8c3a17a..44f927641b89 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atomfirmware.c @@ -204,6 +204,7 @@ amdgpu_atomfirmware_get_vram_info(struct amdgpu_device *adev, (mode_info->atom_context->bios + data_offset); switch (crev) { case 11: + case 12: mem_channel_number = igp_info->v11.umachannelnumber; /* channel width is 64 */ if (vram_width) -- cgit v1.2.3 From beaf10efca64ac824240838ab1f054dfbefab5e6 Mon Sep 17 00:00:00 2001 From: Alex Deucher Date: Wed, 1 Jul 2020 12:00:08 -0400 Subject: drm/amdgpu: use %u rather than %d for sclk/mclk Large clock values may overflow and show up as negative. Reported by prOMiNd on IRC. Acked-by: Nirmoy Das Signed-off-by: Alex Deucher Cc: stable@vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c index 16596a9ccabe..02e6f8c4dde0 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_pm.c @@ -2784,7 +2784,7 @@ static ssize_t amdgpu_hwmon_show_sclk(struct device *dev, if (r) return r; - return snprintf(buf, PAGE_SIZE, "%d\n", sclk * 10 * 1000); + return snprintf(buf, PAGE_SIZE, "%u\n", sclk * 10 * 1000); } static ssize_t amdgpu_hwmon_show_sclk_label(struct device *dev, @@ -2819,7 +2819,7 @@ static ssize_t amdgpu_hwmon_show_mclk(struct device *dev, if (r) return r; - return snprintf(buf, PAGE_SIZE, "%d\n", mclk * 10 * 1000); + return snprintf(buf, PAGE_SIZE, "%u\n", mclk * 10 * 1000); } static ssize_t amdgpu_hwmon_show_mclk_label(struct device *dev, -- cgit v1.2.3